| { | |
| "best_metric": 0.6231209635734558, | |
| "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_mrpc_128/checkpoint-203", | |
| "epoch": 12.0, | |
| "global_step": 348, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.6471, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6238649487495422, | |
| "eval_runtime": 0.8931, | |
| "eval_samples_per_second": 456.836, | |
| "eval_steps_per_second": 4.479, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.6304, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6241526007652283, | |
| "eval_runtime": 0.7361, | |
| "eval_samples_per_second": 554.307, | |
| "eval_steps_per_second": 5.434, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.6314, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6248883008956909, | |
| "eval_runtime": 0.7328, | |
| "eval_samples_per_second": 556.792, | |
| "eval_steps_per_second": 5.459, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.6307, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6250340342521667, | |
| "eval_runtime": 0.7264, | |
| "eval_samples_per_second": 561.693, | |
| "eval_steps_per_second": 5.507, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6298, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6232542395591736, | |
| "eval_runtime": 0.7106, | |
| "eval_samples_per_second": 574.171, | |
| "eval_steps_per_second": 5.629, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.6283, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6232870221138, | |
| "eval_runtime": 0.7277, | |
| "eval_samples_per_second": 560.678, | |
| "eval_steps_per_second": 5.497, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.6283, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6231209635734558, | |
| "eval_runtime": 0.734, | |
| "eval_samples_per_second": 555.856, | |
| "eval_steps_per_second": 5.45, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.6224, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6265362501144409, | |
| "eval_runtime": 0.7212, | |
| "eval_samples_per_second": 565.718, | |
| "eval_steps_per_second": 5.546, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.6042, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6355301141738892, | |
| "eval_runtime": 0.7284, | |
| "eval_samples_per_second": 560.148, | |
| "eval_steps_per_second": 5.492, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5862, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6303420662879944, | |
| "eval_runtime": 0.7331, | |
| "eval_samples_per_second": 556.564, | |
| "eval_steps_per_second": 5.457, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.5717, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6323529411764706, | |
| "eval_combined_score": 0.6924140943506116, | |
| "eval_f1": 0.7524752475247526, | |
| "eval_loss": 0.6515097618103027, | |
| "eval_runtime": 0.7306, | |
| "eval_samples_per_second": 558.416, | |
| "eval_steps_per_second": 5.475, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.5641, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6412438750267029, | |
| "eval_runtime": 0.7454, | |
| "eval_samples_per_second": 547.372, | |
| "eval_steps_per_second": 5.366, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "step": 348, | |
| "total_flos": 1050778043154432.0, | |
| "train_loss": 0.61455181275291, | |
| "train_runtime": 328.2232, | |
| "train_samples_per_second": 558.766, | |
| "train_steps_per_second": 4.418 | |
| } | |
| ], | |
| "max_steps": 1450, | |
| "num_train_epochs": 50, | |
| "total_flos": 1050778043154432.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |